Abstract: A method includes receiving an input audio signal that corresponds to utterances spoken by multiple speakers. The method also includes processing the input audio to generate a transcription of the utterances and a sequence of speaker turn tokens each indicating a location of a respective speaker turn. The method also includes segmenting the input audio signal into a plurality of speaker segments based on the sequence of speaker tokens. The method also includes extracting a speaker-discriminative embedding from each speaker segment and performing spectral clustering on the speaker-discriminative embeddings to cluster the plurality of speaker segments into k classes. The method also includes assigning a respective speaker label to each speaker segment clustered into the respective class that is different than the respective speaker label assigned to the speaker segments clustered into each other class of the k classes.

Abstract: A method (500) includes receiving, from an application (50) executing on a client device (110), at a speech service interface (200), configuration parameters (211) for integrating a speech service (250) into the application. The configuration parameters include a language pack directory (225) that maps a primary language code (235) to an on-device path of a primary language pack (110) of the speech service for use in recognizing speech in a primary language and each of one or more codeswitch language codes to an on-device path. The method also includes receiving audio data (102) characterizing an utterance (106) and processing, using a language ID predictor model (230), the audio data to determine that the audio data is associated with the primary language code. The method also includes processing, using the primary language pack, the audio data to determine a transcription (120) that includes one or more words in the primary language.

Abstract: A method includes receiving an input audio signal that corresponds to utterances spoken by multiple speakers. The method also includes processing the input audio to generate a transcription of the utterances and a sequence of speaker turn tokens each indicating a location of a respective speaker turn. The method also includes segmenting the input audio signal into a plurality of speaker segments based on the sequence of speaker tokens. The method also includes extracting a speaker-discriminative embedding from each speaker segment and performing spectral clustering on the speaker-discriminative embeddings to cluster the plurality of speaker segments into k classes. The method also includes assigning a respective speaker label to each speaker segment clustered into the respective class that is different than the respective speaker label assigned to the speaker segments clustered into each other class of the k classes.

Abstract: A method includes receiving audio data including a plurality of spoken terms spoken by one or more speakers during a conversation. The method includes generating diarization results based on the plurality of spoken terms spoken by the one or more speakers during the conversation. The diarization results include a speech recognition result including a series of predicted terms and a series of identity-agnostic speaker tokens. The method also includes processing the diarization results conditioned on a diarization prompt to predict, as output from an LLM, updated diarization results. The updated diarization results include the speech recognition result including the series of predicted terms and a series of identity-specific speaker tokens.

Abstract: A method includes receiving an input audio signal that corresponds to utterances spoken by multiple speakers. The method also includes processing the input audio to generate a transcription of the utterances and a sequence of speaker turn tokens each indicating a location of a respective speaker turn. The method also includes segmenting the input audio signal into a plurality of speaker segments based on the sequence of speaker tokens. The method also includes extracting a speaker-discriminative embedding from each speaker segment and performing spectral clustering on the speaker-discriminative embeddings to cluster the plurality of speaker segments into k classes. The method also includes assigning a respective speaker label to each speaker segment clustered into the respective class that is different than the respective speaker label assigned to the speaker segments clustered into each other class of the k classes.

Abstract: A system for automated rendezvous, docking, and capture of autonomous underwater vehicles at the conclusion of a mission comprising of comprised of a docking rod having lighted, pulsating (in both frequency and light intensity) series of LED light strips thereon, with the LEDs at a known spacing, and the autonomous underwater vehicle specially designed to detect and capture the docking rod and then be lifted structurally by a spherical end strop about which the vehicle can be pivoted and hoisted up (e.g., onto a ship). The method of recovery allows for very routine and reliable automated recovery of an unmanned underwater asset.

Abstract: A system for automated rendezvous, docking, and capture of autonomous underwater vehicles at the conclusion of a mission comprising of comprised of a docking rod having lighted, pulsating (in both frequency and light intensity) series of LED light strips thereon, with the LEDs at a known spacing, and the autonomous underwater vehicle specially designed to detect and capture the docking rod and then be lifted structurally by a spherical end strop about which the vehicle can be pivoted and hoisted up (e.g., onto a ship). The method of recovery allows for very routine and reliable automated recovery of an unmanned underwater asset.

Abstract: A system for automated rendezvous, docking, and capture of autonomous underwater vehicles at the conclusion of a mission comprising of comprised of a docking rod having lighted, pulsating (in both frequency and light intensity) series of LED light strips thereon, with the LEDs at a known spacing, and the autonomous underwater vehicle specially designed to detect and capture the docking rod and then be lifted structurally by a spherical end strop about which the vehicle can be pivoted and hoisted up (e.g., onto a ship). The method of recovery allows for very routine and reliable automated recovery of an unmanned underwater asset.

Abstract: A system for automated rendezvous, docking, and capture of autonomous underwater vehicles at the conclusion of a mission comprising of comprised of a docking rod having lighted, pulsating (in both frequency and light intensity) series of LED light strips thereon, with the LEDs at a known spacing, and the autonomous underwater vehicle specially designed to detect and capture the docking rod and then be lifted structurally by a spherical end strop about which the vehicle can be pivoted and hoisted up (e.g., onto a ship). The method of recovery allows for very routine and reliable automated recovery of an unmanned underwater asset.

Abstract: Software for storing and distributing media in a local area network is disclosed. The software comprises library software and player. The library software manages encrypted media files, for example, video files, and sends them to the player on request. The media files may be chapterised and the player may request one or more chapters. The player decodes the encrypted file and displays it. The player improves performance by using predictive chapter buffering, requesting the transfer of the next chapter from the library at time so that the file is completely received and ready to play at the time the current media playing is complete. The player minimizes the number of requests to the library by automatically creating a public folder of received files so that requests for one of the received files in the folder are transferred from the library to the player.